Електронний науковий архів

Національного університету "Львівська політехніка"

Архів зберігає опубліковані наукові матеріали переважно працівників Університету. Також доступна можливість "самоархівування"


Communities in DSpace

Select a community to browse its collections.

Now showing 1 - 3 of 3

Recent Submissions

Investigation of serverless architecture
(Lviv Politechnic Publishing House, 2021) Lakhai, Vladyslav; Bachynskyy, Ruslan; Lviv Polytechnic National University
Serverless computing is a new and still evolving type of cloud computing, which brings a new approach to the development of information systems. The main idea of serverless is to give an approach of doing computing without dealing with a server to a user. Such approach allows to reduce the cost of the system building and system support. It allows small companies to concentrate on their own system designing instead of thinking about infrastructure building and supporting. Also, a big problem of providing the system security on high level is on cloud’s provider engineering support service. Serverless approach allows to start business quickly without huge initial investment. There is an attempt to completely analyze features, benefits and drawbacks of serverless approach, its use cases and main patterns of Serverless architecture. What is more, different providers have been analyzed.
Analysis of algorithms for searching objects in images using convolutional neural network
(Lviv Politechnic Publishing House, 2021) Koval , Ihor; Lviv Polytechnic National University
The problem of finding objects in images using modern computer vision algorithms has been considered. The description of the main types of algorithms and methods for finding objects based on the use of convolutional neural networks has been given. A comparative analysis and modeling of neural network algorithms to solve the problem of finding objects in images has been conducted. The results of testing neural network models with different architectures on data sets VOC2012 and COCO have been presented. The results of the study of the accuracy of recognition depending on different hyperparameters of learning have been analyzed. The change in the value of the time of determining the location of the object depending on the different architectures of the neural network has been investigated.
Recommendation system for purchasing goods based on the decision tree algorithm
(Lviv Politechnic Publishing House, 2021) Kohut, Yurii; Yurchak, Iryna; Lviv Polytechnic National University
Over the past few years, interest in applications related to recommendation systems has increased significantly. Many modern services create recommendation systems that, based on user profile information and his behavior. This services determine which objects or products may be interesting to users. ecommendation systems are a modern tool for understanding customer needs. The main methods of constructing recommendation systems are the content-based filtering method and the collaborative filtering method. This article presents the implementation of these methods based on decision trees. The content-based filtering method is based on the description of the object and the customer's preference profile. An object description is a finite set of its descriptors, such as keywords, binary descriptors, etc., and a preference profile is a weighted vector of object descriptors in which scales reflect the importance of each descriptor to the client and its contribution to the final decision. This model selects items that are similar to the customer's favorite items before. The second model, which implements the method of collaborative filtering, is based on information about the history of behavior of all customers on the resource: data on their purchases, ssessments of product quality, reviews, marked product. The model finds clients that are similar in behavior and the recommendation is based on their assessments of this element. Voting was used to combine the results issued by individual models – the best result is chosen from the results of two models of the ensemble. This approach minimizes the impact of randomness and averages the errors of each model. The aim: The purpose of work is to create real competitive ecommendation system for short period of time and minimum costs.
Assessing the human condition in medical cyber physical system based on microservice architecture
(Lviv Politechnic Publishing House, 2021) Havano, Bohdan; Morozov , Mykola; Lviv Polytechnic National University; Technical University of Munich
The goal of the work is to propose architectural and information model for assessing the human condition on the basis of microservice architecture in medical cyberphysical system, which, in contrast to the known models for assessing the human condition, can simultaneously provide scaling, fault tolerance and increase the speed of human condition assessment. The theoretical substantiation and the new decision of an actual scientific problem of development and research means of an estimation of a human condition in medical cyber-physical system have been considered. These means involve the parallel processing of data on vital signs of the human condition, organizing the means of information processing into separate independent logical elements – microservices, in comparison with other existing medical cyber-physical systems. An architectural model based on microservice architecture has been proposed.
Methods of vehicle recognition and detecting traffic rules violations on motion picture based on opencv framework
(Lviv Politechnic Publishing House, 2021) Fastiuk, Yevhen; Bachynskyy, Ruslan; Huzynets, Nataliia; Lviv Polytechnic National University
In this era, people using vehicles is getting increased day by day. As pedestrians leading a dog for a walk, or hurrying to their workplace in the morning, we’ve all experienced unsafe, fast-moving vehicles operated by inattentive drivers that nearly mow us down. Many of us live in apartment complexes or housing neighborhoods where ignorant drivers disregard safety and zoom by, going way too fast. To plan, monitor and also control these vehicles is becoming a big challenge. In the article, we have come up with a solution to the above problem using the video surveillance considering the video data from the traffic cameras. Using computer vision and deep learning technology we will be able to recognize violations of rules. This article will describe modern CV and DL methods to recognize vehicle on the road and traffic violations of rules by them. Implementation of methods can be done using OpenCV Python as a tool. Our proposed solution can recognize vehicles, track their speed and help in counting the objects precisely.